CN108109139A - Airborne LIDAR three-dimensional building object detecting method based on gray scale volume element model - Google Patents
Airborne LIDAR three-dimensional building object detecting method based on gray scale volume element model Download PDFInfo
- Publication number
- CN108109139A CN108109139A CN201711362017.1A CN201711362017A CN108109139A CN 108109139 A CN108109139 A CN 108109139A CN 201711362017 A CN201711362017 A CN 201711362017A CN 108109139 A CN108109139 A CN 108109139A
- Authority
- CN
- China
- Prior art keywords
- volume elements
- building
- gray scale
- voxel
- airborne lidar
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Abstract
The present invention proposes a kind of airborne LIDAR three-dimensional building object detecting method based on gray scale volume element model, and this method is:Original airborne LIDAR cloud data is read, forms original airborne LIDAR cloud data collection;Original airborne LIDAR cloud data rule is turned into gray scale 3D voxel data collection;Building roof volume elements detection is carried out to gray scale 3D voxel datas collection;Based on buffer zone analysis, the detection of building facade volume elements is carried out to gray scale 3D voxel datas collection.This method fully utilizes the geometry of LIDAR data and radiation information and make use of in 3D voxel datas the neighborhood relationships implied between each volume elements well, contributes to the airborne LIDAR Point Cloud Processing based on volume elements theory and the development of application.
Description
Technical field
The invention belongs to Remote Sensing Data Processing technical fields, and in particular to a kind of based on the airborne of gray scale volume element model
LIDAR three-dimensional building object detecting methods.
Background technology
City is detected automatically from airborne laser radar (Light Detection And Ranging, LIDAR) cloud data
Area's target is the important topic studied in recent decades.Airborne LIDAR can provide high-precision, it is highdensity it is discrete repeatedly return
Ripple 3D point cloud data, and the strength information of each secondary echo of complete documentation.This is automatic for city target particularly building target
Detection provides abundant information.The classical building object detecting method based on airborne LIDAR cloud data can be divided into following several
Class:Method, Mathematical Morphology Method, digital image processing method, mode identification method and fusion LIDAR data based on fitting
With other types of aviation image or the method for GIS data.The above method use data structure form mainly have discrete point cloud,
Grid grid and irregular triangle network.Discrete point cloud data structure is true 3D data structures, but its space neighborhood information is difficult to profit
With thus causing the difficult design of the building detection algorithm based on cloud;Grid grid and the same of irregular triangle network are put down
Face (X, Y) coordinate can only correspond to elevation (Z) value, and the expression of such data structure is necessarily deposited for 3D LIDAR cloud datas
In information loss, and then influence the integrality of the object detection results based on the class formation.As it can be seen that classical building object detecting method
Used data structure is unfavorable for playing the technical advantage of the true 3D of airborne LIDAR.Voxel data structure is a kind of true 3D numbers
According to structure, information loss will not be caused by expressing LIDAR cloud datas with it.Meanwhile it is implied between the volume elements of the inside configuration several
What topological relation, thus the design of the data processing algorithm based on the data structure is relatively easy.Based on the airborne of volume elements structure
The analysis of LIDAR data be more common in forestry or associated ground target detection, it is of the invention then innovatively by volume elements structure
It is combined with building target detection, it is proposed that the 3D building target detection methods based on voxel data structural model.
The content of the invention
In view of the deficiencies of the prior art, the present invention proposes a kind of airborne LIDAR three-dimensional building based on gray scale volume element model
Object detecting method.
A kind of airborne LIDAR three-dimensional building object detecting method based on gray scale volume element model, comprises the following steps:
Step 1:Original airborne LIDAR cloud data is read, forms original airborne LIDAR cloud data collection;
Step 2:Original airborne LIDAR cloud data rule is turned into gray scale 3D voxel data collection;
Step 2.1:The rejecting abnormalities data from original airborne LIDAR cloud data obtain removal abnormal data set;
Step 2.2:Removal abnormal data set rule is turned into gray scale 3D voxel data collection;
Step 3:Building roof volume elements detection is carried out to gray scale 3D voxel datas collection;
Step 3.1:Elevation hopping behavior based on building marginal point concentrates search building from gray scale 3D voxel datas
Edge volume elements is as seed voxel Vk, wherein, k=1,2 ...;
Step 3.2:To any unlabelled seed voxel Vk, depth-first traversal gray scale 3D voxel datas are concentrated and seed
Volume elements Vk3D is connected and gray scale difference is less than gray difference threshold TgAll unmarked volume elements, and labeled as Ll, until mark is all
With seed voxel Vk3D is connected and gray scale difference is less than gray difference threshold TgVolume elements set, i.e. building roof volume elements set,
In, l be mark label index, l=1,2 ...;
Step 3.3:Based on area performance, density feature and strength characteristics, building roof volume elements set is optimized,
Complete building roof detection;
Step 4:Based on buffer zone analysis, the detection of building facade volume elements is carried out to gray scale 3D voxel datas collection.
The step 2.1 specifically comprises the following steps:
Step 2.1.1:The frequency of each laser point height value in original airborne LIDAR cloud data is counted, and with Nogata
The form visualization of figure shows statistical result;
Step 2.1.2:Determine highest elevation threshold value T corresponding with real terrainhWith lowest elevation threshold value Tl;
Step 2.1.3:For each laser point in original airborne LIDAR cloud data, if its height value is high higher than highest
Journey threshold value ThOr less than lowest elevation threshold value Tl, then the laser point is abnormal data, is rejected, otherwise retains the laser point, most
Removal abnormal data set is obtained eventually.
The step 2.2 specifically comprises the following steps:
Step 2.2.1:3d space scope is represented with the oriented bounding box of removal abnormal data;
Step 2.2.2:According to removal abnormal data the equalization point spacing of laser point is concentrated to determine volume elements in the x, y, z-directions
Resolution ratio (Δ x, Δ y, Δ z), i.e. voxel size;
Step 2.2.3:According to voxel resolution, (Δ x, Δ y, Δ z) divide oriented bounding box, obtain 3D volume elements
Grid, each 3D volume elements grid unit is volume elements;
Step 2.2.4:Each laser point is concentrated to be mapped to 3D volume elements grid removal abnormal data, and then according to 3D volume elements
The Intensity attribute of the laser point included in grid is each volume elements assignment, obtains gray scale 3D voxel data collection.
The step 3.2 specifically comprises the following steps:
3.2.1:An empty stack is initialized, by VkIn deposit stack and it is marked as building volume elements;
3.2.2:A stack top element is popped up from stack top, acquisition is connected with stack top element 3D and gray scale difference is less than gray scale difference
Threshold value TgAll unlabelled volume elements, labeled as building volume elements and be stored in stack;
3.2.3:Judge whether stack is empty, if so, gray scale 3D voxel datas concentrate owned building roof volume elements quilt
Mark, otherwise, return to step 3.2.2.
The step 3.3 specifically comprises the following steps:
Step 3.3.1:The 3D connected regions of non-building roof are rejected based on area performance;
Step 3.3.2:The 3D connected regions of non-building roof are rejected based on density feature;
Step 3.3.3:The 3D connected regions of non-building roof are rejected based on strength characteristics.
The step 4 specifically comprises the following steps:
Step 4.1:Detect the profile of each building roof;
Step 4.2:In the horizontal plane, centered on any building roof profile, using a volume elements as width inwardly
Buffering area is established with outside;
Step 4.3:To any non-zero value volume elements, if it is located at the building that inside buffering area and its gray value is corresponding
The difference of the gray value on roof is less than gray difference threshold Tg, then it is determined as building facade volume elements.
The Intensity attribute of the laser point included in the volume elements grid according to 3D is as follows for the detailed process of each volume elements assignment
It is shown:
Volume elements containing laser point is assigned a value of laser point strength mean value, the volume elements for not containing laser point is assigned a value of 0, into
Each volume elements assignment discretization to { 0 ..., 255 }, is obtained each voxel values by one step.
Beneficial effects of the present invention:
The present invention proposes a kind of airborne LIDAR three-dimensional building object detecting method based on gray scale volume element model, and this method is first
Airborne LIDAR cloud data rule is first turned into gray scale voxel data;Then the elevation hopping behavior of building marginal point is utilized
Building edge volume elements is searched from gray scale voxel data as seed voxel, and mark connected with its 3D and gray value similar in
Whole volume elements are building roof volume elements;Finally it is based on using characteristic of the building facade perpendicular to roof contour to building room
Push up the buffer zone analysis detection building facade volume elements of profile.This method is based on the connective structures of 3D are theoretical so that point cloud
Target information detection in data is converted into the search mark based on volume elements spatial neighborhood relation from traditional approach such as cloud clusters
Mode fully utilizes the geometry of LIDAR data and radiation information and make use of well hidden between each volume elements in 3D voxel datas
The neighborhood relationships contained contribute to the airborne LIDAR Point Cloud Processing based on volume elements theory and the development of application.
Description of the drawings
Fig. 1 is the airborne LIDAR three-dimensional building analyte detection side based on gray scale volume element model in the specific embodiment of the invention
The flow chart of method;
Fig. 2 is original airborne LIDAR cloud data in the specific embodiment of the invention;
Wherein, (a) is Area2 cloud datas, and (b) is Area3 cloud datas, and (c) is the corresponding figure of Area2 cloud datas
Picture, (d) are the corresponding image of Area3 cloud datas;
Fig. 3 is that original airborne LIDAR cloud data rule is turned to gray scale 3D volume elements numbers in the specific embodiment of the invention
According to the flow chart of collection;
Fig. 4 is the stream for carrying out building roof volume elements detection in the specific embodiment of the invention to gray scale 3D voxel datas collection
Cheng Tu;
Fig. 5 is each neighborhood scale schematic diagram in step 3 in the specific embodiment of the invention;
Wherein, (a) is 6 neighborhoods, and (b) is 18 neighborhoods, and (c) is 26 neighborhoods, and (d) is 56 neighborhoods;
Fig. 6 is the gray scale frequency histogram of Area2 in the specific embodiment of the invention;
Fig. 7 is the flow chart that building roof detection is completed in the specific embodiment of the invention;
Fig. 8 is the schematic diagram of setting buffers in the specific embodiment of the invention;
Wherein, dark volume member represents the building roof profile of extraction, and Dark grey volume elements represents inside buffering area, light grey
Volume elements represents outside buffering area;
Fig. 9 be the specific embodiment of the invention in by taking Area3 as an example using the building analyte detection obtained by the method for the present invention
As a result.
Specific embodiment
The specific embodiment of the invention is described in detail below in conjunction with the accompanying drawings.
In present embodiment, used on CPU dual-core 3.5GHz, 7 flagship edition system of memory 4GB, Windows
This method is realized in the programming of MATLAB 7.11.0 platforms, and further passes through the effective of the accuracy assessment verification method to this method
Property.
A kind of airborne LIDAR three-dimensional building object detecting method based on gray scale volume element model, as shown in Figure 1, including following
Step:
Step 1:Original airborne LIDAR cloud data is read, forms original airborne LIDAR cloud data collection.
In present embodiment, using International Photography measurement and remote sensing association (International Society for
Photogrammetry and Remote Sensing, ISPRS) working groups of Section III/4 provide two groups (Area2 and Area3,
As shown in Figure 2) dedicated for target classification test of heuristics city sample data as experimental data, with the effective of the method for inspection
Property and feasibility.Experimental data obtains (500 meters of flying height, field angle 45) by LeicaALS50 airborne lidars instrument.This two groups
Residential block in data comprising the high-rise urban residential building object surrounded by trees and with small annex.Cloud data is close
It spends for 4 points/m2。
In present embodiment, original airborne LIDAR cloud data P={ p are definedi(xi, yi, zi), i=1 ..., n },
In, i is the index of original airborne LIDAR cloud data, and n is the number of original airborne LIDAR cloud data, piIt is former i-th
Beginning airborne LIDAR cloud data, coordinate are (xi, yi, zi)。
Step 2:Original airborne LIDAR cloud data rule is turned into gray scale 3D voxel data collection, idiographic flow such as Fig. 3 institutes
Show.
Step 2.1:The rejecting abnormalities data from original airborne LIDAR cloud data obtain removal abnormal data set.
Step 2.1.1:The frequency of each laser point height value in original airborne LIDAR cloud data is counted, and with Nogata
The form visualization of figure shows statistical result.
Step 2.1.2:Determine highest elevation threshold value T corresponding with real terrainhWith lowest elevation threshold value Tl。
Step 2.1.3:For each laser point in original airborne LIDAR cloud data, if its height value is high higher than highest
Journey threshold value ThOr less than lowest elevation threshold value Tl, then the laser point is abnormal data, is rejected, otherwise retains the laser point, most
Removal abnormal data set is obtained eventually.
In present embodiment, removal abnormal data set is denoted as Q={ qi′(xi′, yi′, zi′), i '=1 ..., t }, wherein, i '
It is to remove the index that abnormal data concentrates data, t is to remove the number that abnormal data concentrates data, qi′It is removal abnormal data set
In the i-th ' a data, coordinate be (xi′, yi′, zi′)。
In present embodiment, highest elevation threshold value ThWith lowest elevation threshold value TlFor constant, value need to be according to original airborne
The space distribution situation of LIDAR cloud datas determines.
Step 2.2:Removal abnormal data set rule is turned into gray scale 3D voxel data collection.
Step 2.2.1:3d space scope is represented with the oriented bounding box of removal abnormal data.
In present embodiment, the oriented bounding box of removal abnormal data set Q is cuboid, and the big I in bottom surface is by asking for
The minimum enclosed rectangle that removal abnormal data set Q is projected on X/Y plane determines that height can be by (zmax-zmin) determine.
Wherein, zmaxIt is the maximum for removing the z coordinate of laser point in abnormal data set Q, zminIt is removal abnormal data set Q
The minimum value of the z coordinate of middle laser point, zmax=max { zi′, i '=1 ..., t }, zmin=min { zi′, i '=1 ..., t }.
Step 2.2.2:Determine volume elements in x, y, z direction according to the equalization point spacing of laser point in removal abnormal data set Q
On resolution ratio (Δ x, Δ y, Δ z), i.e. voxel size.
In present embodiment, volume elements resolution ax x in the x, y, z-directions, Δ y, calculation formula such as formula (1) institute of Δ z
Show:
Wherein, Sxy={ (xi′, yi′), i '=1 ..., t } it is obtained by projections of the removal abnormal data set Q on XOY plane
Two-dimentional point set, C (Sxy) it is point set SxyConvex hull, A (C (Sxy)) it is convex hull C (Sxy) area.
Step 2.2.3:According to voxel resolution, (Δ x, Δ y, Δ z) divide oriented bounding box, obtain 3D volume elements
Grid, each 3D volume elements grid unit is volume elements.
In present embodiment, based on voxel resolution, (oriented bounding box can be divided into 3D bodies by Δ x, Δ y, Δ z)
First grid is represented with 3D volume elements arrays.If V is the volume elements set in 3D volume elements arrays, as shown in formula (2):
V={ vj(rj, cj, lj), j=1 ..., m }, (2)
Wherein, j is volume elements index;M is volume elements number;vjIt is the voxel values of j-th of volume elements;(rj, cj, lj) it is j-th of volume elements
Coordinate (row, column and level number) in volume elements array.Volume elements number in X-direction is R, and the volume elements number in Y-direction is C, Z
Volume elements number on direction is L.Wherein, R, C, L are by formula (3) Suo Shi:
Wherein,For the operator that rounds up, xmax=max { xi′, i '=1 ..., t }, xmin=min { xi′, i '=
1 ..., t }, ymax=max { yi′, i '=1 ..., t }, ymin=min { yi′, i '=1 ..., t }.
It therefore deduces that, shown in volume elements number m such as formulas (4):
M=R*C*L (4)
Step 2.2.4:Each laser point is concentrated to be mapped to 3D volume elements grid removal abnormal data, and then according to 3D volume elements
The Intensity attribute of the laser point included in grid is each volume elements assignment, obtains gray scale 3D voxel data collection.
In present embodiment, each laser point in removal abnormal data set Q is mapped to 3D volume elements grid, and then according to 3D
The Intensity attribute of the laser point included in volume elements grid is each volume elements assignment.Wherein, the volume elements containing laser point is assigned a value of swashing
The volume elements for not containing laser point is assigned a value of 0 by spot intensity average, as shown in formula (5):
Wherein,It is accorded with for downward floor operation.Further by each volume elements assignment discretization to { 0 ..., 255 }, obtain each
Voxel values.Gray scale 3D voxel data collection is obtained as a result, completes the regularization to removing abnormal data set.
Step 3:Building roof volume elements detection is carried out to gray scale 3D voxel datas collection, idiographic flow is as shown in Figure 4.
Step 3.1:Elevation hopping behavior based on building marginal point concentrates search building from gray scale 3D voxel datas
Edge volume elements is as seed voxel Vk, wherein, k=1,2 ....
In present embodiment, for gray scale 3D voxel datas concentrate any non-zero value volume elements, if the non-zero value volume elements and its
The depth displacement of non-zero value volume elements in 8 neighborhood of level is more than height difference threshold value Te(constant, 2 meters), then judge the volume elements for building side
Edge volume elements, as seed voxel Vk。
Step 3.2:To any unlabelled seed voxel Vk, depth-first traversal gray scale 3D voxel datas are concentrated and seed
Volume elements Vk3D is connected and gray scale difference is less than gray difference threshold TgAll unmarked volume elements, and labeled as Ll, until mark is all
With seed voxel Vk3D is connected and gray scale difference is less than gray difference threshold TgVolume elements set, i.e. building roof volume elements set,
In, l be mark label index, l=1,2 ....
3.2.1:An empty stack is initialized, by VkIn deposit stack and it is marked as building volume elements.
3.2.2:A stack top element is popped up from stack top, acquisition is connected with stack top element 3D and gray scale difference is less than gray scale difference
Threshold value TgAll unlabelled volume elements, labeled as building volume elements and be stored in stack.
In present embodiment, volume elements, that is, gray scale difference similar in the voxel values is less than gray difference threshold TgTwo volume elements;
It connects and refers to building volume elements 3D:It is connected with the building volume elements 6,18,26,56 or the connection of other neighborhood scales, such as
Shown in Fig. 5.
3.2.3:Judge whether stack is empty, if so, gray scale 3D voxel datas concentrate owned building roof volume elements quilt
Mark, otherwise, return to step 3.2.2.
In present embodiment, different neighborhood scales and different gray difference threshold T are applied in above-mentioned labeling processgMeeting
Obtain different building roof testing results.Optimal neighborhood scale will determine in an experiment.Optimum gradation difference threshold value is by following
Scheme determines (by taking experimental data Area2 as an example):
The frequency of the gray value of the non-zero value volume elements in 3D volume elements arrays V is counted, and is shown with represented as histograms, such as Fig. 6 institutes
Show, building and ground target, peak value 33 are corresponded to comprising 3 normal distributions, the 2nd normal distribution in figure.In order to ensure
The volume elements for belonging to single building is divided into a 3D connected region, and the 2nd normal distribution corresponding to building is used to
Calculate optimal gray difference threshold Tg.The scope of 2nd normal distribution gray value is [10,90], mean μ and standard deviation sigma point
It is not 45.5 and 19.7.2.3 σ are used as optimal gray difference threshold Tg.The reason for selecting multiplier 2.3 is all buildings
Tonal gradation all in the range of 2.3 σ.
In present embodiment, reference data employs the building normal data (quilt of ISPRS Section III/4 working groups offer
Accurate classification is the experimental data of building point set and non-building point set), with the computational accuracy of quantitative assessment the method for the present invention.
The achievement of building object detecting method proposed by the present invention is represented in the form of volume elements, and the building in reference data
Object is expressed with discrete LIDAR laser point cloud datas.To compare to evaluate side proposed by the present invention with reference data
Method precision counts the number of the original airborne LIDAR cloud data included in the building volume elements that this method is detected, so first
It is compared afterwards with reference data and then (the building laser points correctly detected accounts for building in testing result and swash with accuracy
The ratio of total number of spots), (the building laser points correctly detected account for the sum of building laser point in normal data to integrity degree
Ratio), quality and Kappa coefficients carry out the validity of quantitative assessment building object detecting method proposed by the invention.
Table 1 is in the present embodiment, and when neighborhood scale is respectively 6,8,26,56 and 80,2 are tested using the method for the present invention
Data carry out building analyte detection, the Kappa coefficients of corresponding building testing result.Data in the table are intended to examine or check different necks
Influence of the domain scale to building testing result, and thereby determine that optimal neighborhood scale.
The precision of the building testing result of the different neighborhood scales of table 1
As shown in Table 1, the average Kappa coefficients of 6,18,26,56 and 80 neighborhoods be respectively 62.2%, 73.5%,
75.5%th, 90.7% and 88.6%.This explanation:The Kappa coefficients of (1) 56 neighbor assignment maximum, therefore, refer to from Kappa coefficients
From the point of view of mark, 56 neighborhoods are optimal neighborhood scales;(2) increase of neighborhood scale is not meant to the necessarily raising of accuracy of detection.This
The thought of invention proposition method is that building information can be by based on the connectedness and intensity similarity defined in volume elements array
To propagate.By taking 6 neighborhoods as an example, building information can only be propagated to 6 directions of its up, down, left, right, before and after, thus be caused only
There is the volume elements on flat-top (for example, Area 2) that can just be integrated into a 3D connected region and be correctly detected, and position
Multiple 3D connected regions may be divided into and therefore by follow-up face in the volume elements on fastigium buildings object (for example, Area 3)
Product etc. characteristics and judge by accident.This can explain why the Kappa coefficients of the Area 2 of 6 neighborhoods are far above Area 3.With neighborhood
The increase of scale, the direction of propagation increase, and more volume elements are classified as building, are produced using 18,26,56 neighborhoods than 6 neighborhoods
Raw better result.But if neighborhood scale is too big, some non-building volume elements may be mistaken for building, this can be explained
Why the precision of 80 neighborhoods, 56 neighborhoods of comparison is declined instead.
Step 3.3:Based on area performance, density feature and strength characteristics, building roof volume elements set is optimized,
Complete building roof detection;.
In present embodiment, the characteristic of building roof is:With certain area;With other targets (such as vegetation etc.)
There are density and strength differences for spatial distribution.According to above-mentioned area, density and the strength characteristics of building roof to step 3.2 institute
The 3D connected regions of building roof optimize, that is, reject the 3D connected regions of indivedual non-building roofs present in it
Domain.
Step 3.3.1:The 3D connected regions of non-building roof are rejected based on area performance.
In present embodiment, original airborne LIDAR cloud data is made to integrate the minimum floor area of building in P as Amin, make original
Airborne LIDAR cloud data integrates the floor area of building of the maximum in P as Amax.To any 3D connected regions, if its horizontal plane
Product is more than or equal to AminAnd less than or equal to Amax, then the 3D connected regions be determined as building roof, retained, otherwise rejected
The 3D connected regions.
In the present embodiment, AminAnd AmaxFor constant, by user according to given original airborne LIDAR cloud data
Situation defines.
Step 3.3.2:The 3D connected regions of non-building roof are rejected based on density feature.
In present embodiment, to any 3D connected regions, if its density is more than given density threshold Td, then 3D connections
Regional determination is building roof, is retained, and otherwise rejects the 3D connected regions.
In present embodiment, density threshold TdFor constant, value can be according to the Density Distribution feelings of each 3D connected regions
Condition determines.
Step 3.3.3:The 3D connected regions of non-building roof are rejected based on strength characteristics.
In present embodiment, to any 3D connected regions, if its intensity is less than given intensity threshold Ts, then 3D connections
Regional determination is building roof, is retained, and otherwise rejects the 3D connected regions;
In present embodiment, intensity threshold TsFor constant, value can be according to the Density Distribution feelings of each 3D connected regions
Condition determines.
Step 4:Based on buffer zone analysis, the detection of building facade volume elements is carried out to gray scale 3D voxel datas collection, it is specific to flow
Journey is as shown in Figure 7.
Step 4.1:Detect the profile of each building roof.
Step 4.2:In the horizontal plane, centered on any building roof profile, using a volume elements as width inwardly
Buffering area is established with outside, as shown in Figure 8..
Step 4.3:To any non-zero value volume elements, if it is located at the building that inside buffering area and its gray value is corresponding
The difference of the gray value on roof is less than gray difference threshold Tg, then it is determined as building facade volume elements.
In present embodiment, provided by taking Area3 as an example using building testing result such as Fig. 9 institutes obtained by the method for the present invention
Show.Wherein, Area3 includes laser point 237,875, wherein including abnormal data.After rejecting abnormal data, point cloud number subtracts
Less to 237,873.Above-mentioned cloud data turns to gray scale voxel data (scale is 382 × 593 × 63) by rule, wherein including
150098 non-zero value volume elements.By the building detection process based on gray scale volume element model, isolated from above-mentioned volume elements
38392 building volume elements (see black cuboid in Fig. 9, voxel size is 0.4m × 0.4m × 0.4m).Above-mentioned buildings
A kind of directly available 3D buildings meta-models made building model, be new model of member.
Table 2 is in the present embodiment, using reference data is standard to 56 neighborhood rulers of 2 test datas using the method for the present invention
The quantitative assessment that building accuracy of detection under degree carries out.
The precision of 2 building testing result of table
As shown in Table 2:Building analyte detection average integrity degree, accuracy and quality be respectively 97.4%, 89.0% and
91.1%.So as to demonstrate the validity of method proposed by the present invention.
Airborne LIDAR building object detecting method provided by the invention based on volume elements, with the connective structure theories of 3D for base
Plinth so that the target information detection in cloud data is converted into from traditional approach such as cloud clusters based on volume elements spatial neighborhood relation
Search mark mode, make use of in 3D voxel datas the neighborhood relationships implied between each volume elements well, contribute to based on volume elements
Theoretical airborne LIDAR Point Cloud Processing and the development of application.This method is to large-scale, intensive, irregular shape and other rooms
The type more special testing result of complex building its integrity degree in top can reach more than 90%, accuracy up to 85% with
On, it can effectively realize the detection to building.
Finally it should be noted that:The above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations;To the greatest extent
Pipe is described in detail the present invention with reference to foregoing embodiments, it will be understood by those of ordinary skill in the art that:Its according to
Can so modify to the technical solution recorded in foregoing embodiments either to which part or all technical characteristic into
Row equivalent substitution;And these modifications or replacement, the essence of appropriate technical solution is not made to depart from the claims in the present invention and is limited
Fixed scope.
Claims (7)
1. a kind of airborne LIDAR three-dimensional building object detecting method based on gray scale volume element model, which is characterized in that including following step
Suddenly:
Step 1:Original airborne LIDAR cloud data is read, forms original airborne LIDAR cloud data collection;
Step 2:Original airborne LIDAR cloud data rule is turned into gray scale 3D voxel data collection;
Step 2.1:The rejecting abnormalities data from original airborne LIDAR cloud data obtain removal abnormal data set;
Step 2.2:Removal abnormal data set rule is turned into gray scale 3D voxel data collection;
Step 3:Building roof volume elements detection is carried out to gray scale 3D voxel datas collection;
Step 3.1:Elevation hopping behavior based on building marginal point concentrates search building edge from gray scale 3D voxel datas
Volume elements is as seed voxel Vk, wherein, k=1,2 ...;
Step 3.2:To any unlabelled seed voxel Vk, depth-first traversal gray scale 3D voxel datas are concentrated and seed voxel
Vk3D is connected and gray scale difference is less than gray difference threshold TgAll unmarked volume elements, and labeled as Ll, until marking all and seed
Volume elements Vk3D is connected and gray scale difference is less than gray difference threshold TgVolume elements set, i.e. building roof volume elements set, wherein, l is mark
The index of note label, l=1,2 ...;
Step 3.3:Based on area performance, density feature and strength characteristics, building roof volume elements set is optimized, is completed
Building roof detects;
Step 4:Based on buffer zone analysis, the detection of building facade volume elements is carried out to gray scale 3D voxel datas collection.
2. the airborne LIDAR 3D building object detecting methods according to claim 1 based on gray scale volume element model, feature
It is, the step 2.1 specifically comprises the following steps:
Step 2.1.1:The frequency of each laser point height value in original airborne LIDAR cloud data is counted, and with histogram
Form visualization shows statistical result;
Step 2.1.2:Determine highest elevation threshold value T corresponding with real terrainhWith lowest elevation threshold value Tl;
Step 2.1.3:For each laser point in original airborne LIDAR cloud data, if its height value is higher than highest elevation threshold
Value ThOr less than lowest elevation threshold value Tl, then the laser point is abnormal data, is rejected, otherwise retains the laser point, finally obtain
Abnormal data set must be removed.
3. the airborne LIDAR 3D building object detecting methods according to claim 1 based on gray scale volume element model, feature
It is, the step 2.2 specifically comprises the following steps:
Step 2.2.1:3d space scope is represented with the oriented bounding box of removal abnormal data;
Step 2.2.2:According to removal abnormal data the equalization point spacing of laser point is concentrated to determine point of volume elements in the x, y, z-directions
Resolution (Δ x, Δ y, Δ z), i.e. voxel size;
Step 2.2.3:Foundation voxel resolution (Δ x, Δ y, Δ z) divide oriented bounding box, obtain 3D volume elements grid,
Each 3D volume elements grid unit is volume elements;
Step 2.2.4:Each laser point is concentrated to be mapped to 3D volume elements grid removal abnormal data, and then according to 3D volume elements grid
In the Intensity attribute of laser point that includes be each volume elements assignment, obtain gray scale 3D voxel data collection.
4. the airborne LIDAR 3D according to claim 1 based on gray scale volume element model builds object detecting method, feature exists
In the step 3.2 specifically comprises the following steps:
3.2.1:An empty stack is initialized, by VkIn deposit stack and it is marked as building volume elements;
3.2.2:A stack top element is popped up from stack top, acquisition is connected with stack top element 3D and gray scale difference is less than gray difference threshold
TgAll unlabelled volume elements, labeled as building volume elements and be stored in stack;
3.2.3:Judge whether stack is empty, if so, gray scale 3D voxel datas concentrate owned building roof volume elements labeled,
Otherwise, return to step 3.2.2.
5. the airborne LIDAR 3D building object detecting methods according to claim 1 based on gray scale volume element model, feature
It is, the step 3.3 specifically comprises the following steps:
Step 3.3.1:The 3D connected regions of non-building roof are rejected based on area performance;
Step 3.3.2:The 3D connected regions of non-building roof are rejected based on density feature;
Step 3.3.3:The 3D connected regions of non-building roof are rejected based on strength characteristics.
6. the airborne LIDAR 3D building object detecting methods according to claim 1 based on gray scale volume element model, feature
It is, the step 4 specifically comprises the following steps:
Step 4.1:Detect the profile of each building roof;
Step 4.2:In the horizontal plane, centered on any building roof profile, using a volume elements as width inwardly and outside
Buffering area is established in side;
Step 4.3:To any non-zero value volume elements, if it is located at the building roof that inside buffering area and its gray value is corresponding
Gray value difference be less than gray difference threshold Tg, then it is determined as building facade volume elements.
7. the airborne LIDAR according to claim 3 based on volume elements segmentation builds object detecting method, which is characterized in that institute
It states as follows for the detailed process of each volume elements assignment according to the Intensity attribute of the laser point included in 3D volume elements grid:
Volume elements containing laser point is assigned a value of laser point strength mean value, the volume elements for not containing laser point is assigned a value of 0, further
By each volume elements assignment discretization to { 0 ..., 255 }, each voxel values are obtained.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711362017.1A CN108109139B (en) | 2017-12-18 | 2017-12-18 | Airborne LIDAR three-dimensional building detection method based on gray voxel model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711362017.1A CN108109139B (en) | 2017-12-18 | 2017-12-18 | Airborne LIDAR three-dimensional building detection method based on gray voxel model |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108109139A true CN108109139A (en) | 2018-06-01 |
CN108109139B CN108109139B (en) | 2022-01-14 |
Family
ID=62209750
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711362017.1A Active CN108109139B (en) | 2017-12-18 | 2017-12-18 | Airborne LIDAR three-dimensional building detection method based on gray voxel model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108109139B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108961231A (en) * | 2018-06-28 | 2018-12-07 | 中国地震局地震预测研究所 | Building destruction condition detection method |
CN109785261A (en) * | 2019-01-11 | 2019-05-21 | 辽宁工程技术大学 | A kind of airborne LIDAR three-dimensional filtering method based on gray scale volume element model |
CN110717983A (en) * | 2019-09-07 | 2020-01-21 | 苏州工业园区测绘地理信息有限公司 | Building facade three-dimensional reconstruction method based on knapsack type three-dimensional laser point cloud data |
CN111008989A (en) * | 2019-12-24 | 2020-04-14 | 辽宁工程技术大学 | Airborne multi-spectral LIDAR three-dimensional segmentation method based on multi-valued voxel |
CN112067633A (en) * | 2020-09-10 | 2020-12-11 | 张晓锋 | Steel construction building engineering quality intelligent detection system based on machine vision |
CN112099046A (en) * | 2020-09-16 | 2020-12-18 | 辽宁工程技术大学 | Airborne LIDAR three-dimensional plane detection method based on multi-valued voxel model |
CN113516777A (en) * | 2021-05-13 | 2021-10-19 | 天讯方舟(北京)信息科技有限公司 | Three-dimensional automatic modeling and visualization method for urban building |
CN113689444A (en) * | 2021-07-07 | 2021-11-23 | 北京道达天际科技有限公司 | Building point cloud monomer segmentation method and device |
CN113689443A (en) * | 2021-07-07 | 2021-11-23 | 北京道达天际科技有限公司 | Building point cloud contour extraction method and device |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130155058A1 (en) * | 2011-12-14 | 2013-06-20 | The Board Of Trustees Of The University Of Illinois | Four-dimensional augmented reality models for interactive visualization and automated construction progress monitoring |
CN103322911A (en) * | 2013-05-27 | 2013-09-25 | 吴晓军 | Characteristic building elevation surveying and mapping method based on images |
CN103473786A (en) * | 2013-10-13 | 2013-12-25 | 西安电子科技大学 | Gray level image segmentation method based on multi-objective fuzzy clustering |
CN105844602A (en) * | 2016-04-01 | 2016-08-10 | 辽宁工程技术大学 | Airborne LIDAR point cloud 3D filtering method based on volume elements |
CN105844629A (en) * | 2016-03-21 | 2016-08-10 | 河南理工大学 | Automatic segmentation method for point cloud of facade of large scene city building |
CN106145623A (en) * | 2016-06-24 | 2016-11-23 | 佛山市保路威环保材料有限公司 | The application of discarded glass and anti-skid surface colour strengthening glass aggregate preparation method |
CN106324581A (en) * | 2016-08-25 | 2017-01-11 | 辽宁工程技术大学 | Body-element-based airborne LIDAR building detection method |
-
2017
- 2017-12-18 CN CN201711362017.1A patent/CN108109139B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130155058A1 (en) * | 2011-12-14 | 2013-06-20 | The Board Of Trustees Of The University Of Illinois | Four-dimensional augmented reality models for interactive visualization and automated construction progress monitoring |
CN103322911A (en) * | 2013-05-27 | 2013-09-25 | 吴晓军 | Characteristic building elevation surveying and mapping method based on images |
CN103473786A (en) * | 2013-10-13 | 2013-12-25 | 西安电子科技大学 | Gray level image segmentation method based on multi-objective fuzzy clustering |
CN105844629A (en) * | 2016-03-21 | 2016-08-10 | 河南理工大学 | Automatic segmentation method for point cloud of facade of large scene city building |
CN105844602A (en) * | 2016-04-01 | 2016-08-10 | 辽宁工程技术大学 | Airborne LIDAR point cloud 3D filtering method based on volume elements |
CN106145623A (en) * | 2016-06-24 | 2016-11-23 | 佛山市保路威环保材料有限公司 | The application of discarded glass and anti-skid surface colour strengthening glass aggregate preparation method |
CN106324581A (en) * | 2016-08-25 | 2017-01-11 | 辽宁工程技术大学 | Body-element-based airborne LIDAR building detection method |
Non-Patent Citations (2)
Title |
---|
王丽英 等: "结合体元数据结构的机载LIDAR建筑物检测", 《中国图象图形学报》 * |
黄敏儿 等: "利用像素高度图的三维建筑物屋顶和立面提取方法", 《武汉大学学报 信息科学版》 * |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108961231B (en) * | 2018-06-28 | 2021-05-25 | 中国地震局地震预测研究所 | Method for detecting destruction state of building |
CN108961231A (en) * | 2018-06-28 | 2018-12-07 | 中国地震局地震预测研究所 | Building destruction condition detection method |
CN109785261A (en) * | 2019-01-11 | 2019-05-21 | 辽宁工程技术大学 | A kind of airborne LIDAR three-dimensional filtering method based on gray scale volume element model |
CN109785261B (en) * | 2019-01-11 | 2023-03-17 | 辽宁工程技术大学 | Airborne LIDAR three-dimensional filtering method based on gray voxel model |
CN110717983A (en) * | 2019-09-07 | 2020-01-21 | 苏州工业园区测绘地理信息有限公司 | Building facade three-dimensional reconstruction method based on knapsack type three-dimensional laser point cloud data |
CN111008989A (en) * | 2019-12-24 | 2020-04-14 | 辽宁工程技术大学 | Airborne multi-spectral LIDAR three-dimensional segmentation method based on multi-valued voxel |
CN111008989B (en) * | 2019-12-24 | 2023-08-11 | 辽宁工程技术大学 | Airborne multispectral LIDAR three-dimensional segmentation method based on multivalued voxels |
CN112067633B (en) * | 2020-09-10 | 2021-06-18 | 龙元明筑科技有限责任公司 | Steel construction building engineering quality intelligent detection system based on machine vision |
CN112067633A (en) * | 2020-09-10 | 2020-12-11 | 张晓锋 | Steel construction building engineering quality intelligent detection system based on machine vision |
CN112099046A (en) * | 2020-09-16 | 2020-12-18 | 辽宁工程技术大学 | Airborne LIDAR three-dimensional plane detection method based on multi-valued voxel model |
CN113516777A (en) * | 2021-05-13 | 2021-10-19 | 天讯方舟(北京)信息科技有限公司 | Three-dimensional automatic modeling and visualization method for urban building |
CN113689444A (en) * | 2021-07-07 | 2021-11-23 | 北京道达天际科技有限公司 | Building point cloud monomer segmentation method and device |
CN113689443A (en) * | 2021-07-07 | 2021-11-23 | 北京道达天际科技有限公司 | Building point cloud contour extraction method and device |
Also Published As
Publication number | Publication date |
---|---|
CN108109139B (en) | 2022-01-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108109139A (en) | Airborne LIDAR three-dimensional building object detecting method based on gray scale volume element model | |
CN110570428B (en) | Method and system for dividing building roof sheet from large-scale image dense matching point cloud | |
Guo et al. | Classification of airborne laser scanning data using JointBoost | |
Yang et al. | A shape-based segmentation method for mobile laser scanning point clouds | |
Wu et al. | Rapid localization and extraction of street light poles in mobile LiDAR point clouds: A supervoxel-based approach | |
CN112070769B (en) | Layered point cloud segmentation method based on DBSCAN | |
CN105844602B (en) | A kind of airborne LIDAR point cloud three-dimensional filtering method based on volume elements | |
CN108828621A (en) | Obstacle detection and road surface partitioning algorithm based on three-dimensional laser radar | |
CN110047036B (en) | Polar grid-based ground laser scanning data building facade extraction method | |
CN106324581B (en) | A kind of airborne LIDAR building analyte detection method based on volume elements | |
CN111986322B (en) | Point cloud indoor scene layout reconstruction method based on structural analysis | |
CN108074232B (en) | Voxel segmentation-based airborne LIDAR building detection method | |
CN112099046B (en) | Airborne LIDAR three-dimensional plane detection method based on multi-value voxel model | |
CN108764012A (en) | The urban road shaft recognizer of mobile lidar data based on multi-frame joint | |
Guo et al. | Classification of airborne laser scanning data using JointBoost | |
CN109766824B (en) | Active and passive remote sensing data fusion classification method based on fuzzy evidence theory | |
CN116573017A (en) | Urban rail train running clearance foreign matter sensing method, system, device and medium | |
CN109359680B (en) | Explosion sillar automatic identification and lumpiness feature extracting method and device | |
Boerner et al. | Voxel based segmentation of large airborne topobathymetric lidar data | |
CN109785261B (en) | Airborne LIDAR three-dimensional filtering method based on gray voxel model | |
CN110348478B (en) | Method for extracting trees in outdoor point cloud scene based on shape classification and combination | |
Wolf et al. | Applicability of neural networks for image classification on object detection in mobile mapping 3d point clouds | |
CN111507423B (en) | Engineering quantity measuring method for cleaning transmission line channel | |
Dey et al. | Building Boundary Extraction from LiDAR Point Cloud Data | |
Wang et al. | Point cloud classification and accuracy analysis based on feature fusion |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |